Neural Entity Linking: A Survey of Models Based on Deep Learning

TL;DR

This survey reviews recent neural entity linking models based on deep learning, comparing their architectures and performance, and discusses various techniques, applications, and emerging trends in the field since 2015.

Contribution

It systematically categorizes neural entity linking architectures, summarizes key methods, and highlights recent advancements and applications in deep learning-based entity linking.

Findings

Neural EL models outperform classic methods on benchmarks.

Joint detection and disambiguation improve accuracy.

Embedding techniques are central to modern neural EL systems.

Abstract

This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing. Its goal is to systemize design features of neural entity linking systems and compare their performance to the remarkable classic methods on common benchmarks. This work distills a generic architecture of a neural EL system and discusses its components, such as candidate generation, mention-context encoding, and entity ranking, summarizing prominent methods for each of them. The vast variety of modifications of this general architecture are grouped by several common themes: joint entity mention detection and disambiguation, models for global linking, domain-independent techniques including zero-shot and distant supervision methods, and cross-lingual approaches. Since many neural models take advantage of entity and mention/context embeddings to represent their meaning, this work also overviews prominent entity embedding techniques. Finally, the survey touches on applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models based on the Transformer architecture.